Plugins

Layered memory for AI agents: five verbs (wake/work/pit/tomb/close), core layer read every time, archive on demand. Plain markdown, four pages created on first run; survives restarts, model swaps and plugin removal.

Runs Hindsight long-term memory on your own machine: after a one-time uvx --from hindsight-embed@latest hindsight-embed profile create server setup (~450 MB of Python dependencies) and with your own LLM key, the plugin manages the local memory server itself (health probe, start, stop, logs), registers ten hindsight_local_* tools for status, page search, page read, recall, remember and reflect, injects a knowledge-page index once per session, writes each finished turn back into the bank, and extracts facts with your own LLM key. Do not enable it alongside the official @vectorize-io/hindsight-coding-agents plugin: both read the same bank and would inject duplicate context. At session end it writes a handoff snapshot that the next session injects as previous progress. The data directory is configurable (dataDir) and scripts/relocate.mjs moves an existing install to another drive, creating directory junctions where the server hard-codes its paths.

Session manager and session settings for the DSH sidebar: sessions grouped by workspace with archive filters, title search, batch archive and a read-only transcript preview; global and per-workspace name, occupation and instructions injected into the system prompt; optional recent-only and hide-workspace filters for the sidebar.

One main session coordinates several root sessions: a /relay command and 15 peer_* tools for batched status reports, a version-line notice, task-board claims, handoff and wake, repository watch, read-only session inspection, and a web panel. Phone notifications need the DSHA device bridge.

Cache-first context compaction with an optional adaptive economic policy, observation-only by default, without cache-hit or cost-saving guarantees.

Sync DeepSeek Harness sessions and workspace files to a private GitHub repository for cross-device handoff, with sync badges, search and bulk upload, independent local/remote delete, conflict "pick a side", and multi-device-safe index merging.

Adds two entries to the DSH web sidebar above the settings row: a batch picker that groups sessions by workspace, filters them by a search box and moves the selected ones into a recycle bin, and a recycle bin that restores sessions one by one or all at once, or permanently deletes them. The recycle bin keeps its own list in browser storage and hides its sessions by wrapping the host session-visibility check, so it does not use the host archive; a moved session keeps its log on disk until it is permanently deleted. Sessions that are currently running are refused and reported instead of being moved.

Injects your own text into the DeepSeek Harness system prompt as real system sections from a sidebar editor: each section lands after the persona, after the tool docs, or at the very end of the prompt, can be switched on or off, and can resolve {{variables}}; a preview runs the host's own assemble and render pass so you see the exact prompt the next request will send, with empty, duplicate, unknown-variable and oversize sections flagged.

Replaces the signed-in sidebar account name and avatar on this device only, without changing the account or uploading anything.

Connect DeepSeek Harness to the local Codex CLI with dynamic model discovery, image input, Harness-owned tools, and read-only ChatGPT plan and quota display.

Local LoRA and QLoRA fine-tuning in a panel: import JSONL, see a VRAM estimate before training starts, evaluate, and export an adapter. One-click Python venv setup, but you must supply your own Python 3.10+ and an NVIDIA GPU (6 GB or more). Verified end to end on Windows 11 with an RTX 3060 6 GB; the installer refuses non-Windows hosts, so Linux, macOS and other GPUs are unsupported for now.

Signs in to ima.qq.com (Tencent IMA) with a WeChat QR code and runs a localhost OpenAI-compatible relay in front of its SSE chat endpoint, so the four models behind it appear in the picker.

TeleAgent (China Telecom TeleAI "Stellar" agent) model provider for DeepSeek Harness with the working v1 gateway signing: two-round HMAC-SHA256 keyed by the login JWT signature segment, which fixes the 40104 rejections the older local-v1 signing produced. Signs in through a dedicated browser window over the DevTools protocol — the plugin intercepts the login callback the same way the official desktop app does, so nothing has to be copied by hand — and also accepts a pasted token. Ships points balance, daily check-in, an in-composer account chip, and a configurable context window (100K by default, 16K–2M, since the gateway declares no catalogue and the official client ships one shared 100K preset for all three tiers). Cannot be installed alongside anye-99/dsh-codearts-auth: both register the same teleagent provider, and this plugin reuses its credentials and derives its SSE/tool-call parsing from it.

Drag the two handles to resize and move the DSH chat area as a floating window; position and size persist across reloads, and movement is clamped to the conversation pane so it never leaves the screen.

Wallpaper layer behind the whole DeepSeek Harness Web UI, fed by image URLs, local files and folders, or a Wallpaper Engine workshop directory, with opacity, blur and translucent-panel sliders, a slideshow with random order and cross-fade, muted video playback, previous/next keyboard shortcuts, and a per-URL archive that keeps every fetched picture under "Loaded images".

Shows the cost of the current session's latest exchange, meaning everything since your last message, as a CNY amount to the right of the permission control in the composer, calculated from provider-reported token usage at DeepSeek's peak and off-peak prices.

Queues composer messages sent during DeepSeek peak billing hours and delivers them 3 s after the next off-peak window starts. A dock above the composer shows the countdown with send-now / edit / cancel, the queue survives closing the browser or restarting DSH, and attachments are staged on the host.

OpenCode Go control panel: an account pool that rotates A-to-B when a key runs out or stops authenticating, per-account 5-hour/weekly/monthly allowance, per-model spend with remaining quota, capability tags (image, video, text-only, tools, reasoning), a live OpenCode-vs-official cost comparison, and quota routing that falls back to a DeepSeek official subscription on an upstream limit or degradation, then returns after 10 stable minutes - shown as a current-route banner, a status card and desktop switch notices, in 10 UI languages.

Floating Pomodoro dial pinned to the bottom-right of the Harness UI: custom focus, short-break and long-break lengths, a long break that can be switched off entirely, a round counter, and five Web Audio-synthesized alarm sounds with preview, volume and ring duration. No audio assets and no network requests; timer state survives a reload.

A DSH workbench for picking photos from local folders on macOS and Windows: local dedupe, filtering and grouping, AI grid triage and scoring with an image-capable model you supply (the plugin bundles no model, credentials or quota), then human review, calibration and export.

Vietnamese (tiếng Việt) language pack for the DeepSeek Harness Web UI: hand-translated dictionaries for 61 namespaces (3,477 strings) that take effect when Vietnamese is picked in Settings → Language, plus a /vi-sync command that translates strings added by newer plugin versions through the harness translator service.

Renders the chat turn navigator as a clock-like half dial: one graduation per turn, a purple graduation every fifth turn, and a blue needle on the current turn.

Files the settings entries your installed plugins add below the ones dsh ships, behind a divider with a live count, and keeps up automatically as plugins come and go.

Codex History Rail adds a Codex-style turn rail to the left gutter of a DSH conversation, with hover previews, click-to-jump, and saved favorites.